AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Group SLOPE Penalized Low-Rank Tensor Regression

Yang Chen, Ziyan Luo

JMLR 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: High-dimensional estimation theory · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SLOPE-type penalty (TgSLOPE) instead of group LASSO (TgLASSO) to control TgFDRLROD tensor regression · Synthetic Gaussian design, p=2000TgFDR: 0.891 -> 0.007Improved
add sparse group penalty (TgSLOPE) to TLRR without sparsity penalty (ablation)TLRR · Synthetic Gaussian design, p=2000TgFDR: 0.980 -> 0.007Improved
solve TgSLOPE with pDCAe instead of block majorization minimization (TBMM), CPU timeTgSLOPE · Synthetic Gaussian design, p=2000CPU time (s): 2.242 -> 1.081Improved
solve TgSLOPE with pDCAe instead of TBMM, CPU timeTgSLOPE · Synthetic Gaussian design, p=4000CPU time (s): 6.104 -> 2.962Improved
use pDCAe instead of TBMM on HBC data with tolerance 1e-6TgSLOPE · HBC data, tolerance 1e-6CPU time (s): 668.040 -> 99.964Improved
use TgSLOPE instead of TBMM, discovered featuresHBC data · HBC data, tolerance 1e-4Discovery: 242.50 -> 47.95Improved
use TgSLOPE instead of TgLASSO, prediction errorHBC data · HBC data, tolerance 1e-6MSPE: 0.0861 -> 0.0838Improved
add sparsity (TgSLOPE) versus no sparse penalty (TLRR), feature selection on HBC (ablation)TLRR · HBC data, tolerance 1e-4Discovery: 536.30 -> 47.95Improved
increase model size p from 2000 to 6000 (ablation)TgSLOPE · Synthetic Gaussian designTgFDR: 0.007 -> 0.014Hurt
use TgSLOPE versus TgLASSO on estimation error at p=2000TgLASSO · Synthetic Gaussian design, p=2000RgEE: 3.44e-2 -> 5.59e-2Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy